Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubic
    -0.07
     receptive
    -0.07
     Değ
    -0.07
     делать
    -0.07
    ि�
    -0.07
    Authorize
    -0.06
     glaciers
    -0.06
     irregular
    -0.06
    Tmp
    -0.06
    equal
    -0.06
    POSITIVE LOGITS
    .once
    0.06
     TokenType
    0.06
    .struct
    0.06
     /**<
    0.06
    ümüş
    0.06
     occupying
    0.06
     براي
    0.06
    xEB
    0.06
    .Filters
    0.06
    ับการ
    0.06
    Act Density 0.013%

    No Known Activations